Joint latent factors and attributes to discover interpretable preferences in recommendation

Latent factor (LF) models are highly effective in extracting useful knowledge from High-Dimensional and Sparse (HiDS) matrices which are commonly seen in various industrial applications. An LF model usually adopts iterative optimizers, which may consume many iterations to achieve a local optima, resulting in considerable time cost. Hence, how to accelerate the training process of an LF model becomes a highly significant issue. To address it, this work innovatively proposes a randomized latent factor (RLF) model. It incorporates the principle of randomized learning techniques for neural networks into the LF analysis on HiDS matrices to alleviate the computational burden greatly. It also extends the standard learning process for randomized neural networks in context of LF analysis to make the resulting model represent an HiDS matrix correctly. Experimental results on three HiDS matrices from industrial applications demonstrate that compared with state-of-the-art LF models, RLF is able to achieve significantly higher computational efficiency and comparable prediction accuracy for missing data. More importantly, it provides a novel, effective, and efficient approach to LF analysis on HiDS matrices.

Rating prediction using review texts with underlying sentiments

How to extract useful knowledge from a high-dimensional and sparse (HiDS) matrix efficiently is critical for many big data-related applications. A latent factor (LF) model has been widely adopted to address this problem. It commonly relies on an iterative learning algorithm like stochastic gradient descent. However, an algorithm of this kind commonly consumes many iterations to converge, resulting in considerable time cost on large-scale datasets. How to accelerate an LF model's training process without accuracy loss becomes a vital issue. To address it, this study innovatively proposes a <underline xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">m</u> ultilayered-and-randomized <underline xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">l</u> atent <underline xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">f</u> actor (MLF) model. Its main idea is two-fold: a) adopting randomized-learning to train LFs for implementing a ‘one-iteration’ training process for saving time; and 2) adopting the principle of a generally multilayered structure as in a deep forest or multilayered extreme learning machine to structure its LFs, thereby enhancing its representative learning ability. Empirical studies on six HiDS matrices from real applications demonstrate that compared with state-of-the-art LF models, an MLF model achieves significantly higher computational efficiency with satisfactory prediction accuracy. It has the potential to handle LF analysis on a large scale HiDS matrix with real-time requirements.

Cold-start problem is a key challenge in recommender system. In order to solve this problem, we proposed a dynamic latent factor model that combined with attributes of user and item. With the increase of interaction between user and recommender system, our model can automatically adjust its coefficient to achieve a more reasonable and more satisfactory recommendation. The experimental results show that the proposed method can not only alleviate the cold-start problem of new users and new items, but also improve the recommendation accuracy to some extent.

Recommender systems provide personalized recommendations to the users from a large number of possible options in online stores. Matrix factorization is a well-known and accurate collaborative filtering approach for recommender system, which suffers from cold-start problem for new users and items. When new users join the system, it will take some time before they enter some ratings in the system, until that time, there are not enough ratings to learn the matrix factorization model. Using auxiliary data such as user’s demographic, ratings and reviews in relevant domains, is an effective solution to reduce the new user problem. In this paper, we used the data of users activity from auxiliary domains to build domain-independent users representation that could be used to predict users ratings in the target domains. We proposed an iterative method which applied MAX-VAR generalized canonical correlation analysis (GCCA) on user’s latent factors learned from matrix factorization on each domain. Also, to improve the capability of GCCA to learn latent factors for new users, we propose a generalized canonical correlation analysis by inverse sum of selection matrices (GCCA-ISSM) approach, which provides better recommendations in cold-start scenarios. The proposed approach is extended using content-based features like topic models extracted from user’s reviews. We demonstrate the accuracy and effectiveness of the proposed approaches on cross-domain rating predictions using comprehensive experiments on Amazon and MovieLens datasets.

Latent factor models have been widely used for recommendation. Most existing latent factor models mainly utilize the rating information between users and items, although some recently extended models add some auxiliary information to learn a unified latent factor between users and items. The unified latent factor only represents the latent features of users and items from the aspect of purchase history. However, the latent features of users and items may stem from different aspects, e.g., the brand-aspect and category-aspect of items. In this paper, we propose a Neural network based Aspect-level Collaborative Filtering model (NeuACF) to exploit different aspect latent factors. Through modelling rich objects and relations in recommender system as a heterogeneous information network, NeuACF first extracts different aspect-level similarity matrices of users and items through different meta-paths and then feeds an elaborately designed deep neural network with these matrices to learn aspect-level latent factors. Finally, the aspect-level latent factors are effectively fused with an attention mechanism for the top-N recommendation. Extensive experiments on three real datasets show that NeuACF significantly outperforms both existing latent factor models and recent neural network models.

The cold start problem in recommender systems is a long-standing challenge, which requires recommending to new users (items) based on attributes without any historical interaction records. In these recommendation systems, warm users (items) have privileged collaborative signals of interaction records compared to cold start users (items), and these Collaborative Filtering (CF) signals are shown to have competing performance for recommendation. Many researchers proposed to learn the correlation between collaborative signal embedding space and the attribute embedding space to improve the cold start recommendation, in which user and item categorical attributes are available in many online platforms. However, the cold start recommendation is still limited by two embedding spaces modeling and simple assumptions of space transformation. As user-item interaction behaviors and user (item) attributes naturally form a heterogeneous graph structure, in this paper, we propose a privileged graph distillation model (PGD). The teacher model is composed of a heterogeneous graph structure for warm users and items with privileged CF links. The student model is composed of an entity-attribute graph without CF links. Specifically, the teacher model can learn better embeddings of each entity by injecting complex higher-order relationships from the constructed heterogeneous graph. The student model can learn the distilled output with privileged CF embeddings from the teacher embeddings. Our proposed model is generally applicable to different cold start scenarios with new user, new item, or new user-new item. Finally, extensive experimental results on the real-world datasets clearly show the effectiveness of our proposed model on different types of cold start problems, with average 6.6%, 5.6%, and 17.1% improvement over state-of-the-art baselines on three datasets, respectively.

Evaluation Of Recommendation System On A Movie Dataset

Recommender systems are designed to identify the items that a user will like or find useful based on the user's prior preferences and activities. These systems have become ubiquitous and are an essential tool for information filtering and (e-)commerce. Over the years, collaborative filtering, which derive these recommendations by leveraging past activities of groups of users, has emerged as the most prominent approach for solving this problem. This talk will present some of our recent work towards improving the performance of collaborative filtering-based recommender systems and understanding some of their fundamental limitations and characteristics. It will start by analyzing how the ratings that users provide to a set of items relate to their ratings of the set's individual items and, using these insights, will present rating prediction approaches that utilize distant supervision. It will then discuss extensions to approaches based on sparse linear and latent factor models that postulate that users' preferences are a combination of global and local preferences, which are shown to lead to better user modeling and as such improved prediction performance. Finally, the talk will conclude by discussing what can be accurately predicted by latent factor approaches and by analyzing the estimation error of sparse linear and latent factor models and how its characteristics impacts the performance of top N recommendation algorithms.

One important problem of recommender system is rating prediction. In this paper, we use the movie rating data from MovieLens as an example to show how to use users’ attributes to improve the accuracy of rating prediction. Through data analysis, we observe that users having similar attributes tend to share more similar preferences and users with a special attribute have their own preferred items. Based on the two observations, we assume that a user’s rating to an item is determined by both the user intrinsic characteristics and the user common characteristics. Using the widely adopted latent factor model for rating prediction, in our proposed solution, we use two kinds of latent factors to model a user: one for the user intrinsic characteristics and the other for the user common characteristics. The latter encodes the influence of users’ attributes which include user age, gender and occupation. On the other hand, we jointly use user attributes or item category information and rating data for calculating similarity of users or items. The similarity calculating results are used in our proposed latent factor model as a regularization term to regularize users or items latent factors gap. Experimental results on MovieLens show that by incorporating users’ attributes influences, much lower prediction error is achieved than the state-of-the-art models. The prediction error is further reduced by incorporating influences from item category popularity and item popularity.

Recommender systems are essential engines to deliver product recommendations for e-commerce businesses. Successful adoption of recommender systems could significantly influence the growth of marketing targets. Collaborative filtering is a type of recommender system model that uses customers' activities in the past, such as ratings. Unfortunately, the number of ratings collected from customers is sparse, amounting to less than 4%. The latent factor model is a kind of collaborative filtering that involves matrix factorization to generate rating predictions. However, using only matrix factorization would result in an inaccurate recommendation. Several models include product review documents to increase the effectiveness of their rating prediction. Most of them use methods such as TF-IDF and LDA to interpret product review documents. However, traditional models such as LDA and TF-IDF face some shortcomings, in that they show a less contextual understanding of the document. This research integrated matrix factorization and novel models to interpret and understand product review documents using LSTM and word embedding. According to the experiment report, this model significantly outperformed the traditional latent factor model by more than 16% on an average and achieved 1% on an average based on RMSE evaluation metrics, compared to the previous best performance. Contextual insight of the product review document is an important aspect to improve performance in a sparse rating matrix. In the future work, generating contextual insight using bidirectional word sequential is required to increase the performance of e-commerce recommender systems with sparse data issues.

The 'Cold Start' problem, characterized by insufficient transaction history leading to inefficient personalization, represents one of the frequent challenges encountered in e-commerce systems. This issue, along with data sparsity resulting from limited product interactions, further complicates the reliability of conventional recommendation engines. The objective of this research is to design a novel hybridized recommendation system that enhances both security and suggestion accuracy by dynamically adapting to user interactions in digital environments. By leveraging contextual information and sequential user behavior patterns, the proposed method addresses gaps left by traditional recommender systems. A research methodology is employed that integrates context awareness and sequential pattern mining, combining conventional and advanced recommendation techniques within a unified framework. This hybrid strategy tackles challenges posed by Cold Start scenarios while optimizing the use of scarce user interaction data. Preliminary findings indicate that the hybrid approach significantly improves recommendation performance, particularly in settings with limited historical data. By utilizing contextual and sequential information, the proposed system outperforms existing methods in terms of accuracy and personalization. In conclusion, the study demonstrates the effectiveness of hybrid recommendation systems in addressing fundamental e-commerce challenges such as data sparsity and the Cold Start problem. The adaptability of the approach enables accurate predictions without requiring extensive user history. Future research will focus on the scalability of this strategy across diverse e-commerce platforms to deliver more individualized user experiences.

Recommender systems are powerful tools that filter and recommend content/information relevant to a given user. Collaborative filtering is the most popular technique used in building recommender systems and it has been successfully incorporated in many applications. These conventional recommendation systems require a minimum number of users, items, and ratings in order to provide effective recommendations. This results in the infamous cold-start problem where the system is not able to produce effective recommendations for new users. Recently, there has been an escalation in the popularity and usage of social networks, which persuades people to share their experiences in the form of reviews and ratings on social media. The components of social media such as the influence of friends, interests, and enjoyment create the opportunities to develop solutions for sparsity and cold start problems of recommendation systems. This paper aims to observe these patterns and analyze three of the existing social recommendation systems, SocialMF, SocialFD, and GraphRec. SocialMF and SocialFD algorithms are based on matrix factorization and distance metric learning respectively whereas GraphRec is an attention based deep learning model. Through extensive experimentation with the datasets that these algorithms were tested on and one new dataset, we compared the results based on evaluation metrics including Root Mean Squared Error (RMSE) and Mean Absolute Error (MAE). To investigate how trust impacts the performance of these models, we evaluated them by modifying the trust and social component. Experimental results show that there is no conclusive evidence that trust propagation plays a major part in these models. Moreover, these models show a slightly improved performance in the absence of trust statements.

The limits of conventional recommender systems, such collaborative filtering, have made it more difficult to find suitable content inside large digital movie archives given the explosive growth of online streaming services. A issue known as the cold start problem, these systems often suffer from data sparsity, insufficient scalability, and an incapacity to efficiently accommodate new clients or products. This work uses Long Short-Term Memory (LSTM) networks, a type of Recurrent Neural Network (RNN) adept in gathering long-term dependencies in sequential user activity, hence improving the accuracy and personalizing power of movie suggestions. Using the MovieLens data, we developed and trained an LSTM-based recommender model applying strict preprocessing, temporal modeling, and dynamic learning rate approaches. Experimental evaluations utilizing standard metrics like RMSE, MAE, and Precision@10 show that the LSTM-based system beats conventional approaches included as collaborative filtering, matrix factorization, and neural collaborative filtering. The results show that over time modeling user preferences greatly improves the quality of suggestions. The findings show that LSTM networks offer a feasible and efficient way to create scalable, context-aware recommender systems, therefore enhancing user pleasure and involvement in the digital entertainment industry.

Collaborative filtering is one of the most common scenarios and popular\nresearch topics in recommender systems. Among existing methods, latent factor\nmodels, i.e., learning a specific embedding for each user/item by\nreconstructing the observed interaction matrix, have shown excellent\nperformances. However, such user-specific and item-specific embeddings are\nintrinsically transductive, making it difficult to deal with new users and new\nitems unseen during training. Besides, the number of model parameters heavily\ndepends on the number of all users and items, restricting its scalability to\nreal-world applications. To solve the above challenges, in this paper, we\npropose a novel model-agnostic and scalable Inductive Embedding Module for\ncollaborative filtering, namely INMO. INMO generates the inductive embeddings\nfor users (items) by characterizing their interactions with some template items\n(template users), instead of employing an embedding lookup table. Under the\ntheoretical analysis, we further propose an effective indicator for the\nselection of template users/items. Our proposed INMO can be attached to\nexisting latent factor models as a pre-module, inheriting the expressiveness of\nbackbone models, while bringing the inductive ability and reducing model\nparameters. We validate the generality of INMO by attaching it to both Matrix\nFactorization (MF) and LightGCN, which are two representative latent factor\nmodels for collaborative filtering. Extensive experiments on three public\nbenchmarks demonstrate the effectiveness and efficiency of INMO in both\ntransductive and inductive recommendation scenarios.\n